Knowledge enhancement method and device for plant factory large model

Abstract

The application provides a plant factory large model knowledge enhancement method, comprising: a knowledge presetting step, presetting a knowledge graph of a plant factory, the knowledge graph comprising a plurality of knowledge entities, and storing first real-time data of a knowledge entity in a node attribute of the knowledge entity; a knowledge acquisition step, retrieving the knowledge graph to acquire the node attribute and relationship organization of the knowledge entity required when triggering intelligent decision-making; and an intelligent decision-making step, making intelligent decision-making according to the node attribute and relationship organization of the knowledge entity. The application also provides a plant factory large model knowledge enhancement device, a storage medium and an electronic device. Therefore, the application can improve the precision, real-time and efficiency of intelligent decision-making of the plant factory large model.

Description

Technical Field

[0001] This invention relates to the field of AI large-scale model technology for plant factories, and in particular to a knowledge enhancement method, device, storage medium and electronic device for a large-scale model of a plant factory. Background Technology

[0002] In plant factories, using large AI models for intelligent decision-making suffers from issues such as poor timeliness and insufficient depth of domain knowledge. The inference phase, which utilizes external knowledge sources to provide references for the large model, is currently the most widely used knowledge augmentation technology in industry, fundamentally addressing the problems of model illusion and outdated knowledge. Specifically, after receiving a user's question, the large model first retrieves relevant knowledge fragments from external sources. Then, it uses the "question + retrieved knowledge" as input to generate an answer based on that knowledge, achieving evidence-based generation. Currently, the main methods for implementing external knowledge include real-time web retrieval, accessing knowledge bases, and invoking knowledge graphs.

[0003] In the context of large-scale intelligent decision-making in plant factories, if typical knowledge base or knowledge graph knowledge augmentation techniques are used, the stored knowledge is mostly fixed and updated infrequently. This fails to synchronously acquire dynamic data such as environmental parameters (e.g., temperature, humidity, light intensity) and daily agricultural product prices, leading to a disconnect between the knowledge retrieved by the large model and the actual production scenario, resulting in decisions lacking adaptability to the current situation. If real-time retrieval (sensor data and daily price data from the plant factory) knowledge augmentation techniques are used, on the one hand, it results in redundant context length; on the other hand, real-time data lacks structured organization, making it difficult for the large model to identify the logical relationships between data points, easily leading to data confusion, decision bias, and failing to fully leverage the reference value of real-time data.

[0004] The core reason for the aforementioned shortcomings is that existing knowledge augmentation technologies fail to balance the dynamic nature of real-time production data in plant factories with the input logic requirements of large-scale models. They lack an adaptation mechanism for real-time data and knowledge systems, and cannot simultaneously address the lag of static knowledge and the disorder of real-time data, ultimately affecting the accuracy and timeliness of large-scale model decisions. In our research on intelligent decision-making in large-scale plant factories, this invention found that static knowledge bases or knowledge graphs cannot obtain some highly real-time data, such as environmental data and daily price data from plant factories. However, directly feeding this highly real-time data as retrieved knowledge to the large-scale model without processing may result in excessively long context lengths, and the large-scale model may not be able to understand its logical relationships.

[0005] In conclusion, the existing technology obviously has inconveniences and defects in practical use, so it is necessary to improve it. Summary of the Invention

[0006] To address the aforementioned shortcomings, the present invention aims to provide a knowledge enhancement method, apparatus, storage medium, and electronic device for a large-scale plant factory model, which can improve the accuracy, real-time performance, and efficiency of intelligent decision-making in the large-scale plant factory model.

[0007] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0008] In a first aspect, embodiments of the present invention provide a knowledge enhancement method for a large-scale plant factory model, comprising:

[0009] The knowledge pre-setting step involves pre-setting a knowledge graph for the plant factory, which includes multiple knowledge entities. The first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities.

[0010] The knowledge acquisition step involves retrieving the knowledge graph when intelligent decision-making is triggered, and obtaining the node attributes and relationship organization of the required knowledge entities.

[0011] The intelligent decision-making process involves making intelligent decisions based on the node attributes and relationship organization of the knowledge entity.

[0012] The knowledge enhancement method for the large-scale plant factory model according to the present invention further includes, after the knowledge acquisition step and before the intelligent decision-making step:

[0013] In the knowledge update step, when retrieving the knowledge graph, it is determined whether the node attributes of the corresponding knowledge entity need to be updated. If so, the node attributes are updated and sent to the plant factory model. If not, the node attributes are sent directly to the plant factory model.

[0014] The knowledge enhancement method for a large-scale plant factory model according to the present invention further includes the knowledge updating step comprising:

[0015] After the plant factory big model obtains the node attributes of the knowledge entity, it retrieves the current real-time second real-time data of the knowledge entity.

[0016] Determine whether the second real-time data is consistent with the first real-time data;

[0017] If they match, the node attributes are sent directly to the large plant factory model.

[0018] Otherwise, update the node attributes, update the first real-time data to the second real-time data, and send the updated node attributes to the plant factory large model.

[0019] According to the knowledge enhancement method for the large-scale plant factory model of the present invention, the first real-time data and the second real-time data include environmental parameters collected in real time by the sensors of the plant factory and / or real-time price data of agricultural products obtained from the Internet.

[0020] Secondly, embodiments of the present invention provide a knowledge enhancement device for a large-scale plant factory model, comprising:

[0021] The knowledge preset module is used to preset the knowledge graph of the plant factory. The knowledge graph includes multiple knowledge entities, and the first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities.

[0022] The knowledge acquisition module is used to retrieve the knowledge graph and obtain the node attributes and relationship organization of the required knowledge entities when intelligent decision-making is triggered.

[0023] The intelligent decision-making module is used to make intelligent decisions based on the node attributes and relationship organization of the knowledge entity.

[0024] The knowledge enhancement device for the large-scale plant factory model according to the present invention further includes:

[0025] The knowledge update module is used to determine whether the node attributes of the corresponding knowledge entity need to be updated when retrieving the knowledge graph. If they need to be updated, the node attributes are updated and sent to the plant factory model. If they do not need to be updated, the node attributes are sent directly to the plant factory model.

[0026] According to the knowledge enhancement device for a large-scale plant factory model of the present invention, the knowledge update module is further configured to, after the large-scale plant factory model obtains the node attribute of the knowledge entity, retrieve the current real-time second real-time data of the knowledge entity; determine whether the second real-time data is consistent with the first real-time data; if consistent, directly send the node attribute to the large-scale plant factory model; otherwise, update the node attribute, update the first real-time data to the second real-time data, and send the updated node attribute to the large-scale plant factory model.

[0027] According to the knowledge enhancement device for the large-scale plant factory model of the present invention, the first real-time data and the second real-time data include environmental parameters collected in real time by the sensors of the plant factory and / or real-time price data of agricultural products obtained from the Internet.

[0028] Thirdly, embodiments of the present invention provide a storage medium for storing a computer program for performing any of the methods described herein.

[0029] Fourthly, embodiments of the present invention provide an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement any of the methods described above.

[0030] Therefore, the knowledge enhancement technology for the large-scale plant factory model of the present invention includes: pre-setting a knowledge graph of the plant factory, the knowledge graph including multiple knowledge entities, storing the first real-time data of the knowledge entities in the node attributes of the knowledge entities; when intelligent decision-making is triggered, retrieving the knowledge graph to obtain the node attributes and relationship organization of the knowledge entities required for intelligent decision-making; and making intelligent decisions based on the node attributes and relationship organization of the knowledge entities. Therefore, the present invention can improve the accuracy, real-time performance, and efficiency of intelligent decision-making in the large-scale plant factory model. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating the knowledge enhancement method for the large-scale plant factory model provided in Embodiment 1 of the present invention;

[0032] Figure 2 This is a flowchart illustrating the knowledge enhancement method for the large-scale plant factory model provided in Embodiment 2 of the present invention;

[0033] Figure 3 This is a schematic diagram of the knowledge enhancement device for the large-scale plant factory model provided in Embodiment 3 of the present invention;

[0034] Figure 4 This is a schematic diagram of the knowledge enhancement device for the large-scale plant factory model provided in Embodiment 4 of the present invention;

[0035] Figure 5 This is a schematic diagram of the structure of the electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0037] It should be noted that references to "an embodiment," "embodiment," "example embodiment," etc., in this specification refer to the described embodiment including specific features, structures, or characteristics, but not every embodiment must include these specific features, structures, or characteristics. Furthermore, such expressions do not refer to the same embodiment. Moreover, when describing specific features, structures, or characteristics in conjunction with embodiments, whether or not explicitly described, it is indicated that incorporating such features, structures, or characteristics into other embodiments is within the knowledge of those skilled in the art.

[0038] Furthermore, certain terms are used in the specification and subsequent claims to refer to specific components or parts. Those skilled in the art will understand that manufacturers may use different names or terms to refer to the same component or part. This specification and subsequent claims do not distinguish components or parts by differences in name, but rather by differences in function. The terms "comprising" and "including" used throughout the specification and subsequent claims are open-ended and should be interpreted as "including but not limited to." Additionally, the term "connection" here includes any direct and indirect electrical connection means. Indirect electrical connection means include connections made through other means.

[0039] The knowledge enhancement method for the large-scale plant factory model provided by the present invention will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0040] Research has found that a solution to the shortcomings of existing technologies can be achieved by pre-designing a knowledge graph that conforms to the decision-making logic of plant factories, and then dynamically storing the real-time updated knowledge into the attributes of entity nodes. This allows for intelligent decision-making within the large-scale model of the plant factory, enabling the retrieval of highly real-time data from the knowledge graph. This facilitates the large-scale model of the plant factory in making decisions that are more aligned with the current environment and circumstances of the plant factory.

[0041] The purpose of this invention is to address the shortcomings of existing large-scale model knowledge enhancement technologies in the intelligent decision-making context of plant factories, such as insufficient real-time adaptation and poor logical consistency. It proposes a large-scale model knowledge enhancement method for plant factories that integrates dynamic knowledge graphs. Specifically, it aims to overcome the problem that existing static knowledge sources cannot synchronously acquire dynamic data such as environmental parameters and daily prices of agricultural products in plant factories. It also solves the problems of verbose contexts, difficulty in identifying data association logic, and decision bias caused by directly inputting unprocessed real-time data, ensuring that the large-scale model can make accurate decisions based on structured real-time knowledge that fit the actual production scenario.

[0042] Figure 1 This is a flowchart illustrating the knowledge enhancement method for a large-scale plant factory model provided in Embodiment 1 of the present invention. The method includes the following steps:

[0043] Step S101, knowledge preset step, preset the knowledge graph of the plant factory, the knowledge graph includes multiple knowledge entities, and store the first real-time data of the knowledge entities into the node attributes of the knowledge entities.

[0044] Step S102, knowledge acquisition step: when intelligent decision-making is triggered, the knowledge graph is retrieved to obtain the node attributes and relationship organization of the required knowledge entities.

[0045] Step S103, intelligent decision-making step, makes intelligent decisions based on the node attributes and relationship organization of knowledge entities.

[0046] Key Point 1: Real-time data from the plant factory (environmental parameters, daily prices of agricultural products, etc.) is extracted, processed, and dynamically stored in the entity node attributes of the knowledge graph, enabling real-time knowledge updates. Effect: Overcomes the shortcomings of existing static knowledge sources in terms of real-time performance, ensuring that the knowledge retrieved by the large model is synchronized with the current production scenario, completely resolving decision-making biases caused by knowledge lag.

[0047] Key Point 2: The mapping mechanism between the knowledge graph and the plant factory's real-time data—retrieval-triggered updates. Effect: Maintaining consistency between the knowledge graph data and the data in the plant factory requires high-frequency I / O, which is a waste of resources when the knowledge graph is not in use. Therefore, this invention designs a retrieval-triggered update mechanism to avoid resource waste while ensuring that the retrieved knowledge is up-to-date.

[0048] Key point 3: Organize real-time data in a structured way using knowledge graphs to avoid lengthy contexts caused by directly inputting unprocessed real-time data. Effect: Solves the problems of difficulty in understanding large models and data confusion caused by disordered input of real-time data, reduces the reasoning burden of large models, and ensures that real-time data can be effectively utilized.

[0049] Technical Effects: Compared with existing knowledge enhancement technologies for large-scale intelligent decision-making, this invention has significant and verifiable beneficial effects in the intelligent decision-making scenario of plant factories. (1) Decision-making efficiency is greatly improved. Through a dedicated knowledge graph that conforms to the decision-making logic of plant factories, the structured storage and efficient retrieval of real-time dynamic data are realized, avoiding the redundant time consumption of static knowledge retrieval lag and disordered real-time data processing in existing technologies. This greatly shortens the reasoning cycle of large models, improves the decision response speed, and adapts to the real-time production control needs of plant factories. (2) Decision-making accuracy is significantly improved. This completely solves the problem of model decision-making deviation caused by knowledge lag and chaotic data logic in existing technologies. Relying on the structured knowledge that is updated in real time, the large model decision-making has clear data and logical support, effectively reducing the decision error rate. (3) It is more practical and adaptable. There is no need to add complex hardware investment. Only through the optimized design of the knowledge graph and the real-time data dynamic update mechanism, it not only saves the redundant cost of calling multiple knowledge sources in existing technologies, but also gives full play to the reference value of real-time data, promoting the AI ​​intelligent decision-making of plant factories to upgrade to precision, real-time and efficiency, and has strong industrial application value.

[0050] Figure 2 This is a flowchart illustrating the knowledge enhancement method for a large-scale plant factory model provided in Embodiment 2 of the present invention. The method includes the following steps:

[0051] Step S201, knowledge preset step, preset the knowledge graph of the plant factory, the knowledge graph includes multiple knowledge entities, and store the first real-time data of the knowledge entities into the node attributes of the knowledge entities.

[0052] Step S202, knowledge acquisition step: when intelligent decision-making is triggered, the knowledge graph is retrieved to obtain the node attributes and relationship organization of the required knowledge entities.

[0053] Step S203, knowledge update step: When retrieving the knowledge graph, determine whether the node attributes of the corresponding knowledge entity need to be updated. If so, proceed to step S204; otherwise, proceed to step S205.

[0054] Preferably, this step further includes:

[0055] After obtaining the node attributes of knowledge entities in the large-scale model of the plant factory, the current real-time second real-time data of the knowledge entities is retrieved, and it is determined whether the second real-time data is consistent with the first real-time data.

[0056] If they match, send the node attributes directly to the large plant factory model.

[0057] Otherwise, update the node attributes, update the first real-time data to the second real-time data, and send the updated node attributes to the plant factory large model.

[0058] Step S204: If an update is needed, update the node attributes and send them to the large plant factory model.

[0059] Step S205: If no update is needed, send the node attributes directly to the large model of the plant factory.

[0060] Step S206, Intelligent Decision-Making Step: Make intelligent decisions based on the node attributes and relationship organization of knowledge entities.

[0061] Preferably, the first real-time data and the second real-time data include environmental parameters collected in real time by sensors in the plant factory and / or real-time price data of agricultural products obtained from the Internet.

[0062] A specific implementation of the knowledge enhancement method for the large-scale plant factory model of the present invention includes the following steps:

[0063] Step 1: When the large model of the plant factory needs to make a decision, that is, when the intelligent decision-making function of the large model is triggered, it will automatically retrieve the knowledge graph for knowledge enhancement.

[0064] Step 2: Retrieve the knowledge graph based on the intelligent decision-making trigger conditions of the large model to obtain the knowledge entities (e1, e2, e3, ..., en) and their relationships.

[0065] Step 3: Determine whether the knowledge entity (e1, e2, e3, ..., en) needs to trigger the real-time data update program. If not, directly obtain the attributes of the entity en. If so, proceed to step 4.

[0066] Step 4: Trigger the real-time data update procedure for entity en to obtain the latest attributes of entity en, such as environmental data of the plant factory or internet price data. Finally, organize the knowledge entities (e1, e2, e3, ..., en) and their attributes and relationships into logical knowledge and return it to the large model. The large model will make the final decision based on this knowledge.

[0067] It should be noted that the knowledge enhancement method for the large-scale plant factory model provided in this embodiment of the invention can be executed by an electronic device, a apparatus, or a control module within that apparatus for executing the method. This embodiment of the invention uses an apparatus executing the method as an example to illustrate the knowledge enhancement apparatus for the large-scale plant factory model provided in this embodiment of the invention.

[0068] Figure 3 This is a schematic diagram of the knowledge enhancement device for a large-scale plant factory model provided in Embodiment 3 of the present invention. The knowledge enhancement device 100 for the large-scale plant factory model includes a knowledge pre-setting module 10, a knowledge acquisition module 20, and an intelligent decision-making module 30, wherein:

[0069] The knowledge preset module 10 is used to preset the knowledge graph of the plant factory. The knowledge graph includes multiple knowledge entities, and the first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities.

[0070] The knowledge acquisition module 20 is used to retrieve the knowledge graph and obtain the node attributes and relationship organization of the required knowledge entities when intelligent decision-making is triggered.

[0071] The intelligent decision-making module 30 is used to make intelligent decisions based on the node attributes and relationship organization of knowledge entities.

[0072] Figure 4 This is a schematic diagram of the knowledge enhancement device for a large-scale plant factory model provided in Embodiment 4 of the present invention. The knowledge enhancement device 100 for the large-scale plant factory model includes a knowledge pre-setting module 10, a knowledge acquisition module 20, an intelligent decision-making module 30, and a knowledge updating module 40, wherein:

[0073] The knowledge preset module 10 is used to preset the knowledge graph of the plant factory. The knowledge graph includes multiple knowledge entities, and the first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities.

[0074] The knowledge acquisition module 20 is used to retrieve the knowledge graph and obtain the node attributes and relationship organization of the required knowledge entities when intelligent decision-making is triggered.

[0075] The knowledge update module 40 is used to determine whether the node attributes of the corresponding knowledge entity need to be updated when retrieving the knowledge graph. If they need to be updated, the node attributes are updated and sent to the plant factory big model. If they do not need to be updated, the node attributes are sent directly to the plant factory big model.

[0076] The intelligent decision-making module 30 is used to make intelligent decisions based on the node attributes and relationship organization of knowledge entities.

[0077] Preferably, the knowledge update module 40 is further configured to, after the plant factory big data model obtains the node attributes of the knowledge entity, retrieve the current real-time second real-time data of the knowledge entity. It then determines whether the second real-time data is consistent with the first real-time data. If consistent, the node attributes are directly sent to the plant factory big data model. Otherwise, the node attributes are updated, the first real-time data is updated to the second real-time data, and the updated node attributes are sent to the plant factory big data model.

[0078] Preferably, the first real-time data and the second real-time data include environmental parameters collected in real time by sensors in the plant factory and / or real-time price data of agricultural products obtained from the Internet.

[0079] The knowledge enhancement device for the large-scale plant factory model provided in this embodiment of the invention can achieve... Figures 1-2 The various processes implemented in the knowledge enhancement method embodiment of the plant factory large model shown are not described in detail here to avoid repetition.

[0080] The present invention also provides a storage medium for storing, for example, Figures 1-2 The computer program for any of the knowledge enhancement methods of the large-scale plant factory model. For example, computer program instructions, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the present invention through the operation of the computer, and can achieve the same technical effect. To avoid repetition, they will not be described again here. The program instructions for invoking the methods of the present invention may be stored in a fixed or removable storage medium, and / or transmitted through a data stream in a broadcast or other signal carrying medium, and / or stored in the storage medium of a computer device operating according to the program instructions.

[0081] According to one embodiment of the present invention, the present invention also provides such a Figure 5The illustrated electronic device 400 may optionally include a storage medium 200 for storing a computer program and a processor 300 for executing the computer program. When the computer program is executed by the processor 300, it implements any of the aforementioned knowledge enhancement methods for the large-scale plant factory model, triggering the electronic device 400 to execute methods and / or technical solutions based on the foregoing embodiments, achieving the same technical effect. To avoid repetition, these methods will not be described again here. It should be noted that the electronic devices in this embodiment include mobile electronic devices and non-mobile electronic devices. For example, mobile electronic devices may be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, super mobile personal computers, netbooks, or personal digital assistants, etc., while non-mobile electronic devices may be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This embodiment does not specifically limit the scope of the invention.

[0082] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including associated data structures) can be stored in a computer-readable recording medium, such as RAM memory, a magnetic or optical drive, a floppy disk, or similar devices. Furthermore, some steps or functions of the present invention can be implemented in hardware, for example, as circuitry that works with a processor to perform the various steps or functions.

[0083] This invention can be implemented on a computer as a computer-based method, or in dedicated hardware, or a combination of both. Executable code or portions thereof for the method according to the invention can be stored on a computer program product. Examples of computer program products include memory devices, optical storage devices, integrated circuits, servers, online software, etc. Optionally, the computer program product includes non-transitory program code components stored on a computer-readable medium so as to execute the method according to the invention when the program product is executed on a computer.

[0084] In an optional embodiment, the computer program includes computer program code components adapted to perform all the steps of the method according to the invention when the computer program is run on a computer. Optionally, the computer program is embodied on a computer-readable medium.

[0085] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0086] Of course, the present invention may have other various embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art can make various corresponding changes and modifications according to the present invention, but these corresponding changes and modifications should all fall within the protection scope of the appended claims.

Claims

1. A knowledge enhancement method for a large-scale plant factory model, characterized in that, include: The knowledge pre-setting step involves pre-setting a knowledge graph for the plant factory, which includes multiple knowledge entities. The first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities. The knowledge acquisition step involves retrieving the knowledge graph when intelligent decision-making is triggered, and obtaining the node attributes and relationship organization of the required knowledge entities. The intelligent decision-making process involves making intelligent decisions based on the node attributes and relationship organization of the knowledge entity.

2. The knowledge enhancement method for the large-scale plant factory model according to claim 1, characterized in that, The process following the knowledge acquisition step and before the intelligent decision-making step also includes: In the knowledge update step, when retrieving the knowledge graph, it is determined whether the node attributes of the corresponding knowledge entity need to be updated. If so, the node attributes are updated and sent to the plant factory model. If not, the node attributes are sent directly to the plant factory model.

3. The knowledge enhancement method for the large-scale plant factory model according to claim 2, characterized in that, The knowledge update step further includes: After the plant factory big model obtains the node attributes of the knowledge entity, it retrieves the current real-time second real-time data of the knowledge entity. Determine whether the second real-time data is consistent with the first real-time data; If they match, the node attributes are sent directly to the large plant factory model. Otherwise, update the node attributes, update the first real-time data to the second real-time data, and send the updated node attributes to the plant factory large model.

4. The knowledge enhancement method for the large-scale plant factory model according to claim 3, characterized in that, The first real-time data and the second real-time data include environmental parameters collected in real time by the sensors of the plant factory and / or real-time price data of agricultural products obtained from the Internet.

5. A knowledge enhancement device for a large-scale plant factory model, characterized in that, include: The knowledge preset module is used to preset the knowledge graph of the plant factory. The knowledge graph includes multiple knowledge entities, and the first real-time data of the knowledge entities is stored in the node attributes of the knowledge entities. The knowledge acquisition module is used to retrieve the knowledge graph and obtain the node attributes and relationship organization of the required knowledge entities when intelligent decision-making is triggered. The intelligent decision-making module is used to make intelligent decisions based on the node attributes and relationship organization of the knowledge entity.

6. The knowledge enhancement device for the large-scale plant factory model according to claim 5, characterized in that, Also includes: The knowledge update module is used to determine whether the node attributes of the corresponding knowledge entity need to be updated when retrieving the knowledge graph. If they need to be updated, the node attributes are updated and sent to the plant factory model. If they do not need to be updated, the node attributes are sent directly to the plant factory model.

7. The knowledge enhancement device for a large-scale plant factory model according to claim 6, characterized in that, The knowledge update module is further configured to, after the plant factory big model obtains the node attributes of the knowledge entity, retrieve the current real-time second real-time data of the knowledge entity; and determine whether the second real-time data is consistent with the first real-time data. If they match, the node attributes are sent directly to the plant factory model; otherwise, the node attributes are updated, the first real-time data is updated to the second real-time data, and the updated node attributes are sent to the plant factory model.

8. The knowledge enhancement device for the large-scale plant factory model according to claim 7, characterized in that, The first real-time data and the second real-time data include environmental parameters collected in real time by the sensors of the plant factory and / or real-time price data of agricultural products obtained from the Internet.

9. A storage medium, characterized in that, Used to store a computer program for performing a knowledge enhancement method for a large-scale plant factory model as described in any one of claims 1 to 7.

10. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the knowledge enhancement method for the large-scale plant factory model according to any one of claims 1 to 7.

Images